Jiapu Wang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28176 · open-access PDF
Los grandes modelos de lenguaje (LLM) a menudo luchan con el razonamiento basado en el tiempo porque su memoria paramétrica estática está mal alineada con la evolución dinámica del conocimiento del mundo real. Aunque RAG y Parameter-Efficient Fine-Tuning (PEFT) proporcionan maneras prácticas para mejorar los LLM, siguen siendo insuficientes para el razonamiento temporal. Los métodos de recuperación existentes suelen priorizar la relevancia semántica mientras ignoran la validez temporal, el orden de eventos y las dependencias evolutivas, resultando en evidencias que son relevantes en aislamiento pero temporalmente fragmentadas.
Machine translation (Meta M2M100); the English original follows.
Large Language Models (LLMs) often struggle with temporally grounded reasoning because their static parametric memory is misaligned with the dynamic evolution of real-world knowledge. Although RAG and Parameter-Efficient Fine-Tuning (PEFT) provide practical ways to enhance LLMs, they remain insufficient for temporal reasoning. Existing retrieval methods typically prioritize semantic relevance while overlooking temporal validity, event order, and evolutionary dependencies, resulting in evidence that is relevant in isolation but temporally fragmented. Meanwhile, conventional PEFT methods usually
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28176, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange